#1minPapers Francois Chollet: use LLMs for tree-search instead of next token predictionNot a paper, but 90min of Chollet is always worth watching! The ARC Challenge is fascinating because it’s a rapid adaptation, evolution…14h ago14h ago
#1minPapers “Fourier Analysis Networks” — Yihong Dong et alMulti-layer Perceptrons (MLPs) are the backbones of LLMs, but they aren’t efficient at modeling periodicity (e.g. rhythmic bass in music)…2d ago2d ago
#1minPapers Ability to leverage the tools increases with model params— “Toolformer: Language Models…Yesterday’s #1minPapers noted that model role-play/deception is a problem if models have access to tools. So of course today we’ll dig into…4d ago4d ago
#1minPapers “Role-Play with Large Language Models” - Shanahan et alThe scare a few weeks ago that o1 was able to duplicate its weights via deception got me very interested in how LLMs can role-play. Dug up…5d ago5d ago
#1minPapers “Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement…Got something spicy today: a team at Fudan University in China attempted to reproduce o1. This paper was published 2 wks ago, and full of…Jan 3Jan 3
#1minPapers “Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking” —…I’m fascinated by reasoning: reasoning allows a model to decompose a challenging computation into smaller steps. This Quiet-STaR model…Jan 2Jan 2
#1minPapers “Critique-out-loud Reward Models” — by Zachary Ankner, Mansheej Paul, Brandon Cui…I’m down the rabbit hole of optimized reward models. This paper is still in preprint.Dec 31, 2024Dec 31, 2024
Francois Chollet on true intelligence and ARC challenge #1minPapersNot a paper, but an extremely interesting almost 3hr interview of Francois Chollet. I’ll only focus on takeaways for builders below:Dec 29, 2024Dec 29, 2024
#1minPapers “Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model…#1minPapersDec 28, 2024Dec 28, 2024
An AI Paper A Day #1minPapersI lost a bet fair and square. The “cost” of the bet was to read an AI paper a day for a month. Topics I’ll be focusing on:Dec 28, 2024Dec 28, 2024